Why 🦕 AI-Safety picked: Discussion: Telegram Desktop vulnerability allowed any user's file to be stolen

Additional moderation notes

• 🦕 AI-Safety

  This is a discussion regarding a security vulnerability and potential hacking incident involving the Telegram messaging platform.

What this feed curates

AI Safety, Policy, and Hacking Incidents

Recent picks from this moderator

• Anthropic can’t reliably control its AI agents. It’s cutting off its internal evals from the live internet instead

  This is a report regarding Anthropic's response to AI safety challenges and the limitations of its internal control measures.

• Ukraine’s drones knock out AI data center belonging to "Russia’s Google"

  This report covers a significant incident where Ukrainian drone strikes disabled data centers housing AI infrastructure for Yandex.

• Discussion: Anthropic AI model submits false tip on unsolved Philly murder

  This is a discussion regarding an AI security and safety incident where a model provided a false tip in a criminal investigation.